{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2004.02806","title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","created":"2020-04-01","cited_by_count":397},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2403.04692","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","created":"2024-03-07","cited_by_count":329},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286},{"id":"2410.10733","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","created":"2024-10-14","cited_by_count":217},{"id":"2501.18427","title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer","created":"2025-01-30","cited_by_count":165},{"id":"2405.00666","title":"RGB$\\leftrightarrow$X: Image decomposition and synthesis using material- and lighting-aware diffusion models","created":"2024-05-01","cited_by_count":161},{"id":"1810.09718","title":"Single-Image SVBRDF Capture with a Rendering-Aware Deep Network","created":"2018-10-23","cited_by_count":116},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"id":"2311.16973","title":"DemoFusion: Democratising High-Resolution Image Generation With No $$$","created":"2023-11-24","cited_by_count":107},{"id":"1509.09308","title":"Fast Algorithms for Convolutional Neural Networks","created":"2015-09-30","cited_by_count":102},{"id":"2405.11616","title":"Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention","created":"2024-05-19","cited_by_count":100},{"id":"2503.21758","title":"Lumina-Image 2.0: A Unified and Efficient Image Generative Framework","created":"2025-03-27","cited_by_count":96},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84},{"id":"2310.08579","title":"HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion","created":"2023-10-12","cited_by_count":68},{"id":"2407.02158","title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","created":"2024-07-02","cited_by_count":65},{"id":"2503.18352","title":"Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models","created":"2025-03-24","cited_by_count":65},{"id":"1906.11557","title":"Flexible SVBRDF Capture with a Multi-Image Deep Network","created":"2019-06-27","cited_by_count":50},{"id":"2309.01700","title":"ControlMat: A Controlled Generative Approach to Material Capture","created":"2023-09-04","cited_by_count":50},{"id":"2508.00413","title":"DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space","created":"2025-08-01","cited_by_count":47},{"id":"2401.06056","title":"MatSynth: A Modern PBR Materials Dataset","created":"2024-01-11","cited_by_count":42},{"id":"2308.11408","title":"MatFuse: Controllable Material Generation with Diffusion Models","created":"2023-08-22","cited_by_count":39},{"id":"2406.18459","title":"DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance","created":"2024-06-26","cited_by_count":34},{"id":"2010.00114","title":"MaterialGAN: Reflectance Capture using a Generative SVBRDF Model","created":"2020-09-30","cited_by_count":33},{"id":"2406.06539","title":"MatFusion: A Generative Diffusion Model for SVBRDF Capture","created":"2024-04-24","cited_by_count":31},{"id":"2311.17528","title":"HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models","created":"2023-11-29","cited_by_count":29},{"id":"2311.17060","title":"Material Palette: Extraction of Materials from a Single Image","created":"2023-11-28","cited_by_count":28},{"id":"2206.05649","title":"TileGen: Tileable, Controllable Material Generation and Capture","created":"2022-06-12","cited_by_count":27},{"id":"2304.13172","title":"Generating Procedural Materials from Text or Image Prompts","created":"2023-04-25","cited_by_count":21},{"id":"2305.12296","title":"PhotoMat: A Material Generator Learned from Single Flash Photos","created":"2023-05-20","cited_by_count":18},{"id":"2503.16322","title":"Ultra-Resolution Adaptation with Ease","created":"2025-03-20","cited_by_count":13},{"id":"2207.01044","title":"MatFormer: A Generative Model for Procedural Materials","created":"2022-07-03","cited_by_count":12},{"id":"2312.07315","title":"NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image","created":"2023-12-12","cited_by_count":11},{"id":"2411.04168","title":"DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation","created":"2024-11-06","cited_by_count":11},{"id":"2411.17515","title":"SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates","created":"2024-11-26","cited_by_count":9},{"id":"2412.14148","title":"MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation","created":"2024-12-18","cited_by_count":9},{"id":"2406.14565","title":"ReflectanceFusion: Diffusion-based text to SVBRDF Generation","created":"2024-04-25","cited_by_count":5},{"id":"2306.15679","title":"Generating Parametric BRDFs from Natural Language Descriptions","created":"2023-06-19","cited_by_count":3},{"id":"2404.14676","title":"DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidance","created":"2024-04-23","cited_by_count":2}],"next_cursor":null}